Volley Revolver: A Novel Matrix-Encoding Method for Privacy-Preserving Neural Networks (Inference)

[2201.12577] Volley Revolver: A Novel Matrix-Encoding Method for Privacy-Preserving Neural Networks (Inference) Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Cryptography and Security arXiv:2201.12577 (cs) [Submitted on 29 Jan 2022 ( v1 ), last revised 15 Apr 2026 (this version, v10)] Title: Volley Revolver: A Novel Matrix-Encoding Method for Privacy-Preserving Neural Networks (Inference) Authors: John Chiang View a PDF of the paper titled Volley Revolver: A Novel Matrix-Encoding Method for Privacy-Preserving Neural Networks (Inference), by John Chiang View PDF HTML (experimental) Abstract: In this work, we present a novel matrix-encoding method that is particularly convenient for neural networks to make predictions in a privacy-preserving manner using homomorphic encryption. Based on this encoding method, we implement a convolutional neural network for handwritten image classification over encryption. For two matrices $A$ and $B$ to perform homomorphic multiplication, the main idea behind it, in a simple version, is to encrypt matrix $A$ and the transpose of matrix $B$ into two ciphertexts respectively. With additional operations, the homomorphic matrix multiplication can be calculated over encrypted matrices efficiently. For the convolution operation, we in advance span each convolution kernel to a matrix space of the same size as the input image so as to generate several ciphertexts, each of which is later used together with the ciphertext encrypting input images for calculating some of the final convolution results. We accumulate all these intermediate results and thus complete the convolution operation. In a public cloud with 40 vCPUs, our convolutional neural network implementation on the MNIST testing dataset takes $\sim$ 287 seconds to compute ten likelihoods of 32 encrypted images of size $28 \times 28$ simultaneously. The data owner only needs to upload one ciphertext ($\sim 19.8$ MB) encrypting these 32 images to the public cloud. Comments: The encoding method we proposed in this work, $\texttt{Volley Revolver}$, is particularly tailored for privacy-preserving neural networks. There is a great chance that it can be used to assist the private neural networks training, in which case for the backpropagation algorithm of the fully-connected layer the first matrix $A$ is revolved while the second matrix $B$ is settled to be still Subjects: Cryptography and Security (cs.CR) ; Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2201.12577 [cs.CR] (or arXiv:2201.12577v10 [cs.CR] for this version) https://doi.org/10.48550/arXiv.2201.12577 Focus to learn more arXiv-issued DOI via DataCite Submission history From: John Chiang [ view email ] [v1] Sat, 29 Jan 2022 12:40:19 UTC (1,070 KB) [v2] Sun, 14 Aug 2022 06:44:34 UTC (1,366 KB) [v3] Wed, 29 Mar 2023 12:14:21 UTC (1,366 KB) [v4] Tue, 9 Jan 2024 00:52:21 UTC (662 KB) [v5] Wed, 14 Aug 2024 13:07:13 UTC (200 KB) [v6] Thu, 24 Oct 2024 09:05:36 UTC (201 KB) [v7] Sun, 6 Apr 2025 11:57:26 UTC (201 KB) [v8] Fri, 14 Nov 2025 11:22:31 UTC (224 KB) [v9] Wed, 4 Mar 2026 01:58:25 UTC (234 KB) [v10] Wed, 15 Apr 2026 04:59:41 UTC (235 KB) Full-text links: Access Paper: View a PDF of the paper titled Volley Revolver: A Novel Matrix-Encoding Method for Privacy-Preserving Neural Networks (Inference), by John Chiang View PDF HTML (experimental) TeX Source view license Current browse context: cs.CR < prev | next > new | recent | 2022-01 Change to browse by: cs cs.CV References & Citations NASA ADS Google Scholar Semantic Scholar DBLP - CS Bibliography listing | bibtex export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• A Privacy Preserving System for Movie Recommendations Using Federated Learning#177330
• Geometric Data Perturbation with Noisy-Anchor Alignment for Privacy-Preserving Collaborative Learning#467078
• EI-DDLGN: Efficient Encrypted Inference with Deep Differentiable Logic Gate Networks under TFHE#1071406
• Seq2Synth: Benchmarking Temporal Fidelity in Synthetic Sequential Tabular Data#799005
• Customer churn prediction in privacy-preserving HashCode-based security abstractions.#381028